From b4f41353d07d41d3751a03c019083e81f46e0fc8 Mon Sep 17 00:00:00 2001
From: MichaelRoeder <michaasresearcher@gmail.com>
Date: Wed, 17 Jun 2015 17:31:43 +0200
Subject: [PATCH] Added a simple example class showing the generation of a NIF
 corpus.

---
 .../aksw/gerbil/CorpusGenerationExample.java  | 77 +++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 src/test/java/org/aksw/gerbil/CorpusGenerationExample.java

diff --git a/src/test/java/org/aksw/gerbil/CorpusGenerationExample.java b/src/test/java/org/aksw/gerbil/CorpusGenerationExample.java
new file mode 100644
index 000000000..de90ad5bb
--- /dev/null
+++ b/src/test/java/org/aksw/gerbil/CorpusGenerationExample.java
@@ -0,0 +1,77 @@
+package org.aksw.gerbil;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+
+import org.aksw.gerbil.io.nif.DocumentListParser;
+import org.aksw.gerbil.io.nif.DocumentListWriter;
+import org.aksw.gerbil.io.nif.NIFParser;
+import org.aksw.gerbil.io.nif.NIFWriter;
+import org.aksw.gerbil.io.nif.impl.TurtleNIFParser;
+import org.aksw.gerbil.io.nif.impl.TurtleNIFWriter;
+import org.aksw.gerbil.transfer.nif.Document;
+import org.aksw.gerbil.transfer.nif.NIFTransferPrefixMapping;
+import org.aksw.gerbil.transfer.nif.data.Annotation;
+import org.aksw.gerbil.transfer.nif.data.DocumentImpl;
+import org.aksw.gerbil.transfer.nif.data.TypedNamedEntity;
+import org.junit.Ignore;
+
+import com.hp.hpl.jena.rdf.model.Model;
+import com.hp.hpl.jena.rdf.model.ModelFactory;
+
+/**
+ * This class contains a simple example, showing how a developer could create a
+ * simple NIF corpus.
+ * 
+ * @author Michael R&ouml;der (roeder@informatik.uni-leipzig.de)
+ *
+ */
+@Ignore
+class CorpusGenerationExample {
+
+	public static void main(String[] args) {
+
+		String text = "Japan (Japanese: 日本 Nippon or Nihon) is a stratovolcanic archipelago of 6,852 islands.";
+		Document document = new DocumentImpl(text, "http://example.org/document0");
+
+		// Add the marking for "Japan"
+		Set<String> uris = new HashSet<String>();
+		uris.add("http://example.org/Japan");
+		Set<String> types = new HashSet<String>();
+		types.add("http://example.org/Country");
+		types.add("http://example.org/StratovolcanicArchipelago");
+		document.addMarking(new TypedNamedEntity(0, 5, uris, types));
+
+		// Add the marking for "stratovolcanic archipelago"
+		uris = new HashSet<String>();
+		uris.add("http://example.org/StratovolcanicArchipelago");
+		types = new HashSet<String>();
+		types.add("http://example.org/Archipelago");
+		types.add("http://www.w3.org/2000/01/rdf-schema#Class");
+		document.addMarking(new TypedNamedEntity(42, 26, uris, types));
+
+		// Add a marking showing that this document has geographical content
+		uris = new HashSet<String>();
+		uris.add("http://example.org/Geography");
+		document.addMarking(new Annotation(uris));
+
+		List<Document> documents = new ArrayList<Document>();
+		documents.add(document);
+
+		// Writing our new list of documents to a String
+		NIFWriter writer = new TurtleNIFWriter();
+		String nifString = writer.writeNIF(documents);
+		System.out.println(nifString);
+
+		// After generating a NIF corpus, it can be helpful to parse the NIF using a `NIFParser` instance.
+		NIFParser parser = new TurtleNIFParser();
+		parser.parseNIF(nifString);
+
+		// Instead of text containing the NIF information, a jena RDF `Model` can be created.
+		DocumentListWriter listWriter = new DocumentListWriter();
+		Model nifModel = ModelFactory.createDefaultModel();
+		listWriter.writeDocumentsToModel(nifModel, documents);
+	}
+}